---
title: vae-text-encorder-for-flux-klein-4b
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/vae-text-encorder-for-flux-klein-4b"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/vae-text-encorder-for-flux-klein-4b.md"
repository: AI-ModelScope/vae-text-encorder-for-flux-klein-4b
last_updated: 2026-10-15
license: apache-2.0
base_model:
  - black-forest-labs/FLUX.2-klein-4B
  - black-forest-labs/FLUX.2-klein-base-4B
base_model_relation: finetune
parameters: 15.1B
tensor_type:
  - BF16
  - U8
  - F32
  - F8_E4M3
  - I64
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 31
stars: 0
tags:
  - comfyui
  - diffusion-single-file
---

# vae-text-encorder-for-flux-klein-4b

> vae-text-encorder-for-flux-klein-4b - AI-ModelScope 在 ModelScope 开源的模型。Repackaged model files for ComfyUI.

AI-ModelScope/vae-text-encorder-for-flux-klein-4b 是 ModelScope 魔搭社区上的 15.1B 参数机器学习模型，采用 apache-2.0 许可，基于 black-forest-labs/FLUX.2-klein-4B、black-forest-labs/FLUX.2-klein-base-4B 构建。

- **Repository**: AI-ModelScope/vae-text-encorder-for-flux-klein-4b
- **License**: apache-2.0
- **Parameters**: 15.1B
- **Base model**: black-forest-labs/FLUX.2-klein-4B, black-forest-labs/FLUX.2-klein-base-4B
- **Tags**: comfyui, diffusion-single-file
- **Downloads**: 31
- **Stars**: 0
- **Last updated**: 2026-10-15

Source: https://www.modelscope.cn/models/AI-ModelScope/vae-text-encorder-for-flux-klein-4b

---

# Flux Klein 4B

Repackaged model files for ComfyUI.

Original model repository:

- https://huggingface.co/black-forest-labs/FLUX.2-klein-4B
- https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B

Place the files in the following folders:

```
📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   ├── flux-2-klein-4b.safetensors
│   │   └── flux-2-klein-base-4b.safetensors
│   ├── 📂 text_encoders/
│   │   ├── qwen_3_4b.safetensors
│   │   └── qwen_3_4b_fp4_flux2.safetensors
│   ├── 📂 vae/
│   │   └── flux2-vae.safetensors
```